Instructions to use LibreYOLO/LibreDAMOYOLOm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LibreYOLO
How to use LibreYOLO/LibreDAMOYOLOm with LibreYOLO:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
LibreDAMOYOLOm
DAMO-YOLO-M (TinyNAS_csp backbone, GiraffeNeckV2, ZeroHead with GFL/DFL), 29.2M params, 640x640 input, post-distill release weights, repackaged for LibreYOLO.
COCO val 2017 mAP: 0.5018 (matches upstream's reported 50.2).
Source
Derived from tinyvision/DAMO-YOLO
at commit 319572e (release v0.3.1, post-distill).
The original damoyolo_tinynasL35_M_502.pth checkpoint was hosted on
Alibaba's Aliyun bucket which is now offline. This weight was recovered
from the Internet Archive's Wayback Machine,
snapshot 20250307203542.
Copyright (c) 2021-2022 Alibaba Group Holding Limited. Licensed under the Apache License, Version 2.0.
Modifications
File rename only. damoyolo_tinynasL35_M_502.pth is bit-identical to
LibreDAMOYOLOm.pt. LibreYOLO's nn.Module class hierarchy mirrors
upstream's exactly so model.load_state_dict(...) is strict.
See libreyolo/models/damoyolo/ in the
LibreYOLO source repository
for the architecture port.
License
Apache License 2.0. See the LICENSE and
NOTICE files in this repository.
- Downloads last month
- 83